Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [game-ai]

For questions related to game design involving AI.

1
vote
0answers
30 views

What to study for this simple poker game?

I'm a programmer with a background in mathematics, but I have no experience whatsoever with artificial intelligence/neural networks. I'd like to study it as a hobby, and my goal for now is to solve ...
2
votes
1answer
39 views

Q-Learning tic tac toe - bad player

I tried to build an Q-learning agent which you can play tic tac toe against after training. Unfortunately the agent performs pretty poorly. He tries to win but does not try to make me 'not winning' ...
0
votes
0answers
9 views

Examples of strong symbolic AI for unsolved, non-trivial combinatorial games?

Looking primarily for research papers, but any info or insights on this subject are welcome. Strength does not have to exceed that of the best human player (such as Kasparov), just skilled human ...
1
vote
0answers
6 views

Are fuzzy commands resulting into a general game playing architecture?

During reading some papers about fuzzy systems, I've recognized a subtopic called “fuzzy commands”. The idea is to provide a sentence in natural language, like “move ball to right”, and the fuzzy ...
2
votes
1answer
34 views

Game AI for “Lines” : help to get started

I am trying to find a good approach to create a computer player for the game "Lines" from gamious on Android. The concept of the game is pretty straightforward : Lines is an abstract ‘zen’ game ...
1
vote
1answer
23 views

Why do neural nets and machine learning tend to work well with MCTS, but not with regular Minimax game-playing AI?

I've often heard MCTS grouped together with neural nets and machine learning. From what I gather, MCTS uses a refined intuition (from maching learning) to evaluate positions. This allows it to better ...
1
vote
2answers
33 views

2-dimension input layer?

I am wondering is I can use a 2-dimensions features matrix rather than a feature vector as inout layer of a neural network For a WWII naval wargame, I have sorted out the features of interest to ...
5
votes
1answer
49 views

Incomplete state, Fog of war

I have a steady hex-map and turn-based wargame featuring WWII carrier battles I would like to improve the fixed policy for the AI using reinforcement learning and have some beginner's questions which ...
1
vote
1answer
48 views

Large and Multiple-actions space

I have a steady hex-map and turn-based wargame featuring WWII carrier battles On a given turn, a player may choose different and independent actions 
(moving one, two naval unit, assigning a mission ...
2
votes
1answer
48 views

Wargame — Software and hardware requirement for reinforcement learning

I have a steady hex-map and turn-based wargame featuring WWII carrier battles I would like to improve the fixed policy for the AI using reinforcement learning and have a bunch of noob questions which ...
1
vote
2answers
45 views

Can Alpha–Beta be used on symmetric zero sum games?

This question was asked in an AI exam. How would you answer such question?
0
votes
1answer
60 views

Predicting fate of different actors in upcoming Avengers 4

How would one go about predicting which characters (actors) are going to die in the next Avengers movie. To elaborate a bit, given all leaked scripts (fake or not), interviews of different actors and ...
1
vote
1answer
38 views

Any interesting ways to combine Monte Carlo Search with the standard Minimax/Alpha-beta algorithms?

I've been working on a game-playing engine for about half a year now, and it uses the well known algorithms. These include minimax+alpha-beta pruning, iterative deepening, transposition tables, etc. ...
4
votes
1answer
40 views

How does Hearthstone AI deal with random events

I want to learn a lot about the AI of CCG, such as Hearthstone. And now I have known one of the main algorithms that used in this kind of games, MCTS. It analyses the most promising moves, and expands ...
0
votes
1answer
47 views

which is best approach to choose for game playing problem? [closed]

Which is best approach to choose for game playing problem?
0
votes
2answers
39 views

Genetic programming with “karel the robot”?

Karel the robot is an education software comparable to turtle graphics to teach programming for beginners. It's a virtual stackbased interpreter to run a domain specific language for moving a robot in ...
2
votes
0answers
96 views

Implementing AI/ML for the card game “Cheat”

Background info In Python, I've implemented a rudimentary engine to play "Cheat", supporting both bots and a human or only bots. When only bots are playing, the game is simulated. When placing cards,...
3
votes
0answers
56 views

Old video games intelligence

Around 2000, existed popular fights videogames. There, if you made the same kick movement for several running times, the CPU normally defended and caught your strategy. This is the case in Tekken 3 ie....
3
votes
1answer
27 views

how we find the length(depth) of game tik tok toe in Adversarial search?

when we perform tik tok toe game using adversarial search i know how make tree My Question is : is there any way to find the depth of tree which level is the last level.
1
vote
0answers
42 views

How to encode Azul game state as NN input

Question to NN practicioners. I'd like to encode Azul board game state as an input to NN, let's focus on 2-player variant for a while. There are 5 round "Factories" on the table (7 on picture, ignore ...
3
votes
2answers
106 views

MinMax and enormous branches

I have to build a KI for a made-up game similar to chess. As I did research for a proper solution, I came upon the MinMax algorithm, but I'm not sure it will work with the given game dynamics. The ...
9
votes
2answers
668 views

Is AlphaZero an example of an AGI?

From DeepMind's research paper on arxiv.org: In this paper, we apply a similar but fully generic algorithm, which we call AlphaZero, to the games of chess and shogi as well as Go, without any ...
0
votes
1answer
72 views

How to calculate fitness function of 8-queens problem?

In evolutionary computation and in particular in the context of genetic algorithms, there is a stochastic operation called "fitness function". The better a state, the greater the value of the fitness ...
1
vote
1answer
75 views

DQN Breakout adding an extra negative reward to help training?

I'm trying to train a DQN, so I'm using OpenAI gym and Breakout (Breakout-v0). I have altered the reward supplied by the environment: If the episode is not completed fully, the agent gets a -10 ...
0
votes
0answers
13 views

Task and motion planning with domain specific languages

In a paper published 6 years ago a novel domain specific language (DSL) for character animation was presented. High-level action commands are described in the XML format for authoring a virtual human. ...
0
votes
0answers
13 views

My iterative deepening engine doesn't have an exactly equal score when playing against itself

I made a Connect Four engine that uses the standard minimax/alpha-beta algorithms as its underlying structure, with iterative deepening added on. Because the engine uses iterative deepening, its ...
1
vote
0answers
28 views

Why does Q-learning converges to optimal policy even if I am acting suboptimally?

In Q-learning, during training, it doesn’t matter how I select actions. The algorithm always converges to optimal optimal policy. Why does this happen?
0
votes
1answer
54 views

Is it possible to use a feed-forward neural network to predict the actions in reinforcement learning?

I have done a lot of research on the internet about Reinforcement Learning and I found encountered methods of Reinforcement Learning: Q-Learning and Deep Q-Learning. And I have developed a vague idea ...
1
vote
0answers
25 views

What Actually is Off-Policy Q-Learning?

Recently I have come across an information stating: Q-learning converges to optimal policy -- even if you’re acting suboptimally! It also states: When an optimal policy is still learned from ...
3
votes
1answer
94 views

How to model a plumber dispatcher with Artificial Intelligence?

The domain of emergency call for clogged pipelines has to do with taking a call and managing the reaction of plumber departments. It is mostly a group oriented communication situation between the ...
1
vote
0answers
19 views

How to use Genetic Algorithm for varying lengths of solutions

Until now, I always thought that Genetic Algorithm can be used for problems of which the solution space can be encoded (modeled) as a chromosome of a specific length. However, some people claim that ...
0
votes
1answer
34 views

How do I know how changes in the weights are changing the reward in Reinforcement Learning

I already know the basics of the basic of Machine Learning. E.g.: Backpropagation, Convolution, etc. First of let me explain Reinforcement learning to make sure I grasped the concept correctly. In ...
1
vote
0answers
26 views

Checkers AI game engines

I have coded an AI checkers game but would like to see how good it is. Some people have informed me to use the Chinook AI opensource code. But I am having trouble trying to integrate that software ...
3
votes
1answer
40 views

Transposition table is only used for roughly 17% of the nodes - is this expected?

I'm making a Connect Four game using the typical minimax + alpha-beta pruning algorithms. I just implemented a Transposition Table, but my tests tell me the TT only helps 17% of the time. By this I ...
1
vote
1answer
30 views

Is it meaningful to give more weight to the result of monte carlo search with less turn win?

I'm programming on Connect6 with MCTS. Monte Carlo Tree Search is based on random moves. It counts up the number of wins in certain moves. (Whether it wins in 3 turns or 30 turns) Is the move with ...
0
votes
1answer
37 views

What's the difference between poker with public cards and without them?

Example: texas holdem poker vs texas holdem poker with the same rounds, just with no public cards dealt. Would algorithms like CFR approximate Nash-equilibrium more easily? Could AI that does not ...
0
votes
1answer
55 views

Using a DQN with a variable amount of Valid Moves per turn for a Board Game

I have created a game on an 8x8 grid and there are 4 pieces which can move essentially like checkers pieces (Forward left or Forward right only). I have implemented a DQN in order to pull this off. ...
3
votes
2answers
201 views

Creating a self learning Mario Kart game AI?

I will be undertaking a project over the next year to create a self learning AI to play a racing game, currently the game will be Mario Kart 64. I have a few questions which will hopefully help me ...
0
votes
1answer
42 views

Connect 4 minimax does not make the best move

I'm trying to implement an algorithm that would choose the optimal next move for the game of Connect 4. As I just want to make sure that the basic minimax works correctly, I am actually testing it ...
1
vote
1answer
226 views

Does a solution for Wumpus World with neural networks exist?

The Wumpus World proposed in book of Stuart Russel and Peter Norvig, is a game which happens on a 4x4 board and the objective is to grab the gold and avoiding the threats that can kill you. The rules ...
2
votes
0answers
38 views

Mapping Actions to the Output Layer in Keras Model for a Board Game

I have created a game based on this game here. I am attempting to use Deep Q Learning to do this, and this is my first foray into Neural networks (please be gentle!!) I am trying to create a NN that ...
1
vote
3answers
77 views

Can genetic algorithms be used to learn to play multiple games of the same type?

Is it possible for a genetic algorithm + Neural Network that is used to learn to play one game such as a platform game able to be applied to another different game of the same genre. So for example, ...
0
votes
1answer
73 views

Should Q values be changing within an epoch/episode or should they change after one episode/epoch?

I am trying to use Deep-Q learning environment to learn Super Mario Bros. The implementation is on Github. I have a neural network that Q values update within an episode for a very small learning ...
1
vote
1answer
43 views

Historical weakness of GOFAI in relation to partisan combinatorial games?

I was recently perusing the paper Some Studies in Machine Learning Using the Game of Checkers II--Recent Progress (A.L. Samuel, 1967), which is interesting historically. I was looking at this figure, ...
4
votes
1answer
138 views

Algorithms for games with very high branching factors (Connect6)

Connect6 is an example of a game with a very high branching factor. It is about 45 thousand, dwarfing even the impressive Go. What algorithms can you use on games with such high branching factors? I ...
3
votes
1answer
163 views

Monte Carlo Tree Search Expansion Phase

I'm confused regarding a specific detail of MCTS. To illustrate my question, lets take the simple example of tic-tac-toe. After the selection phase, when a leaf node is reached, the tree is expanded ...
4
votes
2answers
176 views

How to go forward with creating an artifically intelligent aimbot for a game like CS:GO

Artificial Intelligence can be realized as a full autonomous or as a semi-autonomous system. A full autonomous system takes the human operator out of the loop, his hands are away from keyboard and he ...
0
votes
0answers
38 views

Open Ai Gym states become corrupt?

I'm trying to implement a3c for flappy bird using this code https://github.com/awjuliani/DeepRL-Agents/blob/master/A3C-Doom.ipynb. It works perfectly well but what I noticed is that when I save the ...
4
votes
2answers
95 views

Evolving network in game

So I wrote simple feed forward neural network that plays tic-tac-toe: 9 neurons in input layers: 1 - my sign, -1 - opponent's sign, 0 - empty; 9 neurons in hidden layer: value calculated using Relu; ...
5
votes
1answer
70 views

Can you analyse a neural network to determine good states?

I've developed a neural network that can play a card game. I now want to use it to create decks for the game. My first thought would be to run a lot of games with random decks and use some ...